Characterizing the risk of fairwashing

Nov-14-2025, 16:07:12 GMT–Neural Information Processing Systems

In particular, we show that fairwashed explanation models can generalize beyond the suing group ( i.e., data points that are being explained), meaning that

explanation, machine learning, natural language, (15 more...)

Neural Information Processing Systems

Nov-14-2025, 16:07:12 GMT

Conferences PDF

Country:
- Asia > Japan
  - Honshū > Kansai > Osaka Prefecture > Osaka (0.04)
- North America > Canada
  - Quebec > Montreal (0.04)

Genre:
- Research Report > New Finding (1.00)

Technology:
- Information Technology > Artificial Intelligence
  - Issues > Social & Ethical Issues (0.46)
  - Machine Learning
    - Ensemble Learning (0.48)
    - Statistical Learning (0.72)
  - Natural Language > Explanation & Argumentation (0.47)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Characterizing the risk of fairwashing

Similar Docs Excel Report more

Title	Similarity	Source
None found